mteb 2.0.5__py3-none-any.whl → 2.1.1__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- mteb/__init__.py +10 -1
- mteb/_create_dataloaders.py +2 -0
- mteb/abstasks/_stratification.py +1 -1
- mteb/abstasks/abstask.py +6 -1
- mteb/abstasks/dataset_card_template.md +1 -1
- mteb/abstasks/retrieval.py +2 -1
- mteb/abstasks/retrieval_dataset_loaders.py +1 -1
- mteb/abstasks/task_metadata.py +1 -1
- mteb/benchmarks/benchmarks/__init__.py +2 -0
- mteb/benchmarks/benchmarks/benchmarks.py +82 -11
- mteb/benchmarks/get_benchmark.py +1 -1
- mteb/descriptive_stats/Classification/DutchColaClassification.json +54 -0
- mteb/descriptive_stats/Classification/DutchGovernmentBiasClassification.json +54 -0
- mteb/descriptive_stats/Classification/DutchNewsArticlesClassification.json +90 -0
- mteb/descriptive_stats/Classification/DutchSarcasticHeadlinesClassification.json +54 -0
- mteb/descriptive_stats/Classification/IconclassClassification.json +96 -0
- mteb/descriptive_stats/Classification/OpenTenderClassification.json +222 -0
- mteb/descriptive_stats/Classification/VaccinChatNLClassification.json +1068 -0
- mteb/descriptive_stats/Clustering/DutchNewsArticlesClusteringP2P.json +45 -0
- mteb/descriptive_stats/Clustering/DutchNewsArticlesClusteringS2S.json +45 -0
- mteb/descriptive_stats/Clustering/IconclassClusteringS2S.json +48 -0
- mteb/descriptive_stats/Clustering/OpenTenderClusteringP2P.json +111 -0
- mteb/descriptive_stats/Clustering/OpenTenderClusteringS2S.json +111 -0
- mteb/descriptive_stats/Clustering/VABBClusteringP2P.json +60 -0
- mteb/descriptive_stats/Clustering/VABBClusteringS2S.json +60 -0
- mteb/descriptive_stats/Image/Any2AnyMultilingualRetrieval/XFlickr30kCoT2IRetrieval.json +243 -153
- mteb/descriptive_stats/Image/Any2AnyMultilingualRetrieval/XM3600T2IRetrieval.json +999 -629
- mteb/descriptive_stats/Image/Any2AnyRetrieval/OVENIT2TRetrieval.json +33 -17
- mteb/descriptive_stats/Image/DocumentUnderstanding/MIRACLVisionRetrieval.json +574 -0
- mteb/descriptive_stats/MultilabelClassification/CovidDisinformationNLMultiLabelClassification.json +84 -0
- mteb/descriptive_stats/MultilabelClassification/VABBMultiLabelClassification.json +156 -0
- mteb/descriptive_stats/PairClassification/SICKNLPairClassification.json +35 -0
- mteb/descriptive_stats/PairClassification/XLWICNLPairClassification.json +35 -0
- mteb/descriptive_stats/Retrieval/ClimateFEVERHardNegatives.v2.json +30 -0
- mteb/descriptive_stats/Retrieval/DBPediaHardNegatives.v2.json +30 -0
- mteb/descriptive_stats/Retrieval/DutchNewsArticlesRetrieval.json +30 -0
- mteb/descriptive_stats/Retrieval/FEVERHardNegatives.v2.json +30 -0
- mteb/descriptive_stats/Retrieval/HotpotQAHardNegatives.v2.json +30 -0
- mteb/descriptive_stats/Retrieval/LegalQANLRetrieval.json +30 -0
- mteb/descriptive_stats/Retrieval/OpenTenderRetrieval.json +30 -0
- mteb/descriptive_stats/Retrieval/QuoraRetrievalHardNegatives.v2.json +30 -0
- mteb/descriptive_stats/Retrieval/RiaNewsRetrievalHardNegatives.v2.json +30 -0
- mteb/descriptive_stats/Retrieval/VABBRetrieval.json +30 -0
- mteb/descriptive_stats/Retrieval/VDRMultilingualRetrieval.json +184 -0
- mteb/descriptive_stats/Retrieval/bBSARDNLRetrieval.json +30 -0
- mteb/descriptive_stats/STS/SICK-NL-STS.json +28 -0
- mteb/languages/check_language_code.py +11 -3
- mteb/languages/language_scripts.py +4 -0
- mteb/leaderboard/text_segments.py +1 -1
- mteb/models/model_implementations/b1ade_models.py +1 -1
- mteb/models/model_implementations/bge_models.py +1 -3
- mteb/models/model_implementations/bmretriever_models.py +1 -1
- mteb/models/model_implementations/gme_v_models.py +2 -2
- mteb/models/model_implementations/ibm_granite_models.py +1 -1
- mteb/models/model_implementations/inf_models.py +3 -3
- mteb/models/model_implementations/jina_models.py +12 -2
- mteb/models/model_implementations/llm2vec_models.py +1 -1
- mteb/models/model_implementations/misc_models.py +2 -2
- mteb/models/model_implementations/mxbai_models.py +1 -1
- mteb/models/model_implementations/salesforce_models.py +1 -1
- mteb/models/model_implementations/seed_1_6_embedding_models.py +1 -1
- mteb/models/model_implementations/voyage_v.py +9 -9
- mteb/results/task_result.py +6 -8
- mteb/tasks/classification/dan/angry_tweets_classification.py +2 -2
- mteb/tasks/classification/eng/legal_bench_classification.py +3 -3
- mteb/tasks/classification/mya/myanmar_news.py +2 -2
- mteb/tasks/classification/nld/__init__.py +16 -0
- mteb/tasks/classification/nld/dutch_cola_classification.py +38 -0
- mteb/tasks/classification/nld/dutch_government_bias_classification.py +37 -0
- mteb/tasks/classification/nld/dutch_news_articles_classification.py +30 -0
- mteb/tasks/classification/nld/dutch_sarcastic_headlines_classification.py +36 -0
- mteb/tasks/classification/nld/iconclass_classification.py +41 -0
- mteb/tasks/classification/nld/open_tender_classification.py +38 -0
- mteb/tasks/classification/nld/vaccin_chat_nl_classification.py +46 -0
- mteb/tasks/classification/tha/wongnai_reviews_classification.py +1 -1
- mteb/tasks/classification/ukr/ukr_formality_classification.py +2 -2
- mteb/tasks/clustering/__init__.py +1 -0
- mteb/tasks/clustering/nld/__init__.py +17 -0
- mteb/tasks/clustering/nld/dutch_news_articles_clustering_p2p.py +37 -0
- mteb/tasks/clustering/nld/dutch_news_articles_clustering_s2s.py +37 -0
- mteb/tasks/clustering/nld/iconclass_clustering_s2s.py +47 -0
- mteb/tasks/clustering/nld/open_tender_clustering_p2p.py +51 -0
- mteb/tasks/clustering/nld/open_tender_clustering_s2s.py +41 -0
- mteb/tasks/clustering/nld/vabb_clustering_p2p.py +51 -0
- mteb/tasks/clustering/nld/vabb_clustering_s2s.py +51 -0
- mteb/tasks/multilabel_classification/__init__.py +1 -0
- mteb/tasks/multilabel_classification/nld/__init__.py +9 -0
- mteb/tasks/multilabel_classification/nld/covid_disinformation_nl_multi_label_classification.py +88 -0
- mteb/tasks/multilabel_classification/nld/vabb_multi_label_classification.py +44 -0
- mteb/tasks/pair_classification/__init__.py +1 -0
- mteb/tasks/pair_classification/multilingual/indic_xnli_pair_classification.py +9 -8
- mteb/tasks/pair_classification/nld/__init__.py +7 -0
- mteb/tasks/pair_classification/nld/sick_nl_pair_classification.py +36 -0
- mteb/tasks/pair_classification/nld/xlwic_nl_pair_classification.py +41 -0
- mteb/tasks/retrieval/code/code_rag.py +8 -8
- mteb/tasks/retrieval/dan/dan_fever_retrieval.py +1 -1
- mteb/tasks/retrieval/dan/tv2_nordretrieval.py +2 -2
- mteb/tasks/retrieval/dan/twitter_hjerne_retrieval.py +2 -2
- mteb/tasks/retrieval/eng/__init__.py +18 -4
- mteb/tasks/retrieval/eng/climate_fever_retrieval.py +68 -77
- mteb/tasks/retrieval/eng/dbpedia_retrieval.py +55 -50
- mteb/tasks/retrieval/eng/fever_retrieval.py +62 -67
- mteb/tasks/retrieval/eng/hateful_memes_i2t_retrieval.py +0 -4
- mteb/tasks/retrieval/eng/hateful_memes_t2i_retrieval.py +0 -4
- mteb/tasks/retrieval/eng/hotpot_qa_retrieval.py +57 -67
- mteb/tasks/retrieval/eng/legal_summarization_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/memotion_i2t_retrieval.py +0 -3
- mteb/tasks/retrieval/eng/memotion_t2i_retrieval.py +0 -2
- mteb/tasks/retrieval/eng/oven_it2t_retrieval.py +1 -1
- mteb/tasks/retrieval/eng/quora_retrieval.py +51 -46
- mteb/tasks/retrieval/eng/sci_mmir_i2t_retrieval.py +0 -4
- mteb/tasks/retrieval/eng/sci_mmir_t2i_retrieval.py +0 -4
- mteb/tasks/retrieval/eng/vidore_bench_retrieval.py +0 -2
- mteb/tasks/retrieval/jpn/ja_gov_faqs_retrieval.py +1 -1
- mteb/tasks/retrieval/multilingual/belebele_retrieval.py +1 -1
- mteb/tasks/retrieval/multilingual/jina_vdr_bench_retrieval.py +0 -2
- mteb/tasks/retrieval/multilingual/miracl_retrieval.py +1 -1
- mteb/tasks/retrieval/multilingual/miracl_vision_retrieval.py +2 -9
- mteb/tasks/retrieval/multilingual/vidore2_bench_retrieval.py +0 -2
- mteb/tasks/retrieval/multilingual/wit_t2i_retrieval.py +0 -2
- mteb/tasks/retrieval/multilingual/x_flickr30k_co_t2i_retrieval.py +6 -5
- mteb/tasks/retrieval/multilingual/xm3600_t2i_retrieval.py +3 -4
- mteb/tasks/retrieval/nld/__init__.py +10 -0
- mteb/tasks/retrieval/nld/bbsard_nl_retrieval.py +41 -0
- mteb/tasks/retrieval/nld/dutch_news_articles_retrieval.py +30 -0
- mteb/tasks/retrieval/nld/legal_qa_nl_retrieval.py +39 -0
- mteb/tasks/retrieval/nld/open_tender_retrieval.py +38 -0
- mteb/tasks/retrieval/nld/vabb_retrieval.py +41 -0
- mteb/tasks/retrieval/nob/norquad.py +2 -2
- mteb/tasks/retrieval/nob/snl_retrieval.py +2 -2
- mteb/tasks/retrieval/rus/__init__.py +11 -2
- mteb/tasks/retrieval/rus/ria_news_retrieval.py +48 -44
- mteb/tasks/retrieval/tur/tur_hist_quad.py +2 -2
- mteb/tasks/sts/__init__.py +1 -0
- mteb/tasks/sts/nld/__init__.py +5 -0
- mteb/tasks/sts/nld/sick_nl_sts.py +41 -0
- mteb-2.1.1.dist-info/METADATA +253 -0
- {mteb-2.0.5.dist-info → mteb-2.1.1.dist-info}/RECORD +142 -95
- mteb/descriptive_stats/Classification/PersianTextTone.json +0 -56
- mteb/descriptive_stats/Image/Any2TextMutipleChoice/CVBenchCount.json +0 -37
- mteb/descriptive_stats/Image/Any2TextMutipleChoice/CVBenchDepth.json +0 -25
- mteb/descriptive_stats/Image/Any2TextMutipleChoice/CVBenchDistance.json +0 -25
- mteb/descriptive_stats/Image/Any2TextMutipleChoice/CVBenchRelation.json +0 -25
- mteb/descriptive_stats/Image/VisualSTS/STS12VisualSTS.json +0 -20
- mteb/descriptive_stats/Image/VisualSTS/STS13VisualSTS.json +0 -20
- mteb/descriptive_stats/Image/VisualSTS/STS14VisualSTS.json +0 -20
- mteb/descriptive_stats/Image/VisualSTS/STS15VisualSTS.json +0 -20
- mteb/descriptive_stats/Image/VisualSTS/STS16VisualSTS.json +0 -20
- mteb/descriptive_stats/Image/VisualSTS/STS17MultilingualVisualSTS.json +0 -220
- mteb/descriptive_stats/Image/VisualSTS/STSBenchmarkMultilingualVisualSTS.json +0 -402
- mteb/descriptive_stats/Reranking/InstructIR.json +0 -31
- mteb-2.0.5.dist-info/METADATA +0 -455
- {mteb-2.0.5.dist-info → mteb-2.1.1.dist-info}/WHEEL +0 -0
- {mteb-2.0.5.dist-info → mteb-2.1.1.dist-info}/entry_points.txt +0 -0
- {mteb-2.0.5.dist-info → mteb-2.1.1.dist-info}/licenses/LICENSE +0 -0
- {mteb-2.0.5.dist-info → mteb-2.1.1.dist-info}/top_level.txt +0 -0
mteb/descriptive_stats/MultilabelClassification/CovidDisinformationNLMultiLabelClassification.json
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
1
|
+
{
|
|
2
|
+
"test": {
|
|
3
|
+
"num_samples": 252,
|
|
4
|
+
"number_texts_intersect_with_train": null,
|
|
5
|
+
"text_statistics": {
|
|
6
|
+
"total_text_length": 48963,
|
|
7
|
+
"min_text_length": 35,
|
|
8
|
+
"average_text_length": 194.29761904761904,
|
|
9
|
+
"max_text_length": 337,
|
|
10
|
+
"unique_texts": 252
|
|
11
|
+
},
|
|
12
|
+
"image_statistics": null,
|
|
13
|
+
"label_statistics": {
|
|
14
|
+
"min_labels_per_text": 0,
|
|
15
|
+
"average_label_per_text": 2.115079365079365,
|
|
16
|
+
"max_labels_per_text": 6,
|
|
17
|
+
"unique_labels": 7,
|
|
18
|
+
"labels": {
|
|
19
|
+
"1": {
|
|
20
|
+
"count": 183
|
|
21
|
+
},
|
|
22
|
+
"None": {
|
|
23
|
+
"count": 50
|
|
24
|
+
},
|
|
25
|
+
"3": {
|
|
26
|
+
"count": 102
|
|
27
|
+
},
|
|
28
|
+
"5": {
|
|
29
|
+
"count": 83
|
|
30
|
+
},
|
|
31
|
+
"0": {
|
|
32
|
+
"count": 56
|
|
33
|
+
},
|
|
34
|
+
"2": {
|
|
35
|
+
"count": 62
|
|
36
|
+
},
|
|
37
|
+
"4": {
|
|
38
|
+
"count": 47
|
|
39
|
+
}
|
|
40
|
+
}
|
|
41
|
+
}
|
|
42
|
+
},
|
|
43
|
+
"train": {
|
|
44
|
+
"num_samples": 929,
|
|
45
|
+
"number_texts_intersect_with_train": null,
|
|
46
|
+
"text_statistics": {
|
|
47
|
+
"total_text_length": 174673,
|
|
48
|
+
"min_text_length": 33,
|
|
49
|
+
"average_text_length": 188.02260495156082,
|
|
50
|
+
"max_text_length": 714,
|
|
51
|
+
"unique_texts": 929
|
|
52
|
+
},
|
|
53
|
+
"image_statistics": null,
|
|
54
|
+
"label_statistics": {
|
|
55
|
+
"min_labels_per_text": 0,
|
|
56
|
+
"average_label_per_text": 1.9730893433799785,
|
|
57
|
+
"max_labels_per_text": 6,
|
|
58
|
+
"unique_labels": 7,
|
|
59
|
+
"labels": {
|
|
60
|
+
"1": {
|
|
61
|
+
"count": 709
|
|
62
|
+
},
|
|
63
|
+
"3": {
|
|
64
|
+
"count": 377
|
|
65
|
+
},
|
|
66
|
+
"0": {
|
|
67
|
+
"count": 164
|
|
68
|
+
},
|
|
69
|
+
"2": {
|
|
70
|
+
"count": 183
|
|
71
|
+
},
|
|
72
|
+
"4": {
|
|
73
|
+
"count": 138
|
|
74
|
+
},
|
|
75
|
+
"5": {
|
|
76
|
+
"count": 262
|
|
77
|
+
},
|
|
78
|
+
"None": {
|
|
79
|
+
"count": 168
|
|
80
|
+
}
|
|
81
|
+
}
|
|
82
|
+
}
|
|
83
|
+
}
|
|
84
|
+
}
|
|
@@ -0,0 +1,156 @@
|
|
|
1
|
+
{
|
|
2
|
+
"test": {
|
|
3
|
+
"num_samples": 3235,
|
|
4
|
+
"number_texts_intersect_with_train": 2265,
|
|
5
|
+
"text_statistics": {
|
|
6
|
+
"total_text_length": 2927178,
|
|
7
|
+
"min_text_length": 47,
|
|
8
|
+
"average_text_length": 904.8463678516229,
|
|
9
|
+
"max_text_length": 35167,
|
|
10
|
+
"unique_texts": 3235
|
|
11
|
+
},
|
|
12
|
+
"image_statistics": null,
|
|
13
|
+
"label_statistics": {
|
|
14
|
+
"min_labels_per_text": 1,
|
|
15
|
+
"average_label_per_text": 1.8593508500772797,
|
|
16
|
+
"max_labels_per_text": 8,
|
|
17
|
+
"unique_labels": 19,
|
|
18
|
+
"labels": {
|
|
19
|
+
"Social Sciences (General)": {
|
|
20
|
+
"count": 472
|
|
21
|
+
},
|
|
22
|
+
"Sociology": {
|
|
23
|
+
"count": 366
|
|
24
|
+
},
|
|
25
|
+
"Other Disciplines": {
|
|
26
|
+
"count": 557
|
|
27
|
+
},
|
|
28
|
+
"Educational Sciences": {
|
|
29
|
+
"count": 302
|
|
30
|
+
},
|
|
31
|
+
"Economics & Business": {
|
|
32
|
+
"count": 393
|
|
33
|
+
},
|
|
34
|
+
"Social Health Sciences": {
|
|
35
|
+
"count": 255
|
|
36
|
+
},
|
|
37
|
+
"Political Sciences": {
|
|
38
|
+
"count": 201
|
|
39
|
+
},
|
|
40
|
+
"Communication Studies": {
|
|
41
|
+
"count": 155
|
|
42
|
+
},
|
|
43
|
+
"History": {
|
|
44
|
+
"count": 287
|
|
45
|
+
},
|
|
46
|
+
"Humanities (General)": {
|
|
47
|
+
"count": 398
|
|
48
|
+
},
|
|
49
|
+
"Law": {
|
|
50
|
+
"count": 999
|
|
51
|
+
},
|
|
52
|
+
"Philosophy": {
|
|
53
|
+
"count": 233
|
|
54
|
+
},
|
|
55
|
+
"Art History": {
|
|
56
|
+
"count": 349
|
|
57
|
+
},
|
|
58
|
+
"Theology": {
|
|
59
|
+
"count": 58
|
|
60
|
+
},
|
|
61
|
+
"Psychology": {
|
|
62
|
+
"count": 174
|
|
63
|
+
},
|
|
64
|
+
"Criminology": {
|
|
65
|
+
"count": 284
|
|
66
|
+
},
|
|
67
|
+
"Linguistics": {
|
|
68
|
+
"count": 254
|
|
69
|
+
},
|
|
70
|
+
"Literature": {
|
|
71
|
+
"count": 140
|
|
72
|
+
},
|
|
73
|
+
"Archaeology": {
|
|
74
|
+
"count": 138
|
|
75
|
+
}
|
|
76
|
+
}
|
|
77
|
+
}
|
|
78
|
+
},
|
|
79
|
+
"train": {
|
|
80
|
+
"num_samples": 6471,
|
|
81
|
+
"number_texts_intersect_with_train": null,
|
|
82
|
+
"text_statistics": {
|
|
83
|
+
"total_text_length": 5847151,
|
|
84
|
+
"min_text_length": 38,
|
|
85
|
+
"average_text_length": 903.5931077113274,
|
|
86
|
+
"max_text_length": 35167,
|
|
87
|
+
"unique_texts": 6471
|
|
88
|
+
},
|
|
89
|
+
"image_statistics": null,
|
|
90
|
+
"label_statistics": {
|
|
91
|
+
"min_labels_per_text": 1,
|
|
92
|
+
"average_label_per_text": 1.8822438572090867,
|
|
93
|
+
"max_labels_per_text": 11,
|
|
94
|
+
"unique_labels": 19,
|
|
95
|
+
"labels": {
|
|
96
|
+
"Social Sciences (General)": {
|
|
97
|
+
"count": 1021
|
|
98
|
+
},
|
|
99
|
+
"Sociology": {
|
|
100
|
+
"count": 660
|
|
101
|
+
},
|
|
102
|
+
"Other Disciplines": {
|
|
103
|
+
"count": 1124
|
|
104
|
+
},
|
|
105
|
+
"Educational Sciences": {
|
|
106
|
+
"count": 541
|
|
107
|
+
},
|
|
108
|
+
"Economics & Business": {
|
|
109
|
+
"count": 756
|
|
110
|
+
},
|
|
111
|
+
"Linguistics": {
|
|
112
|
+
"count": 501
|
|
113
|
+
},
|
|
114
|
+
"Humanities (General)": {
|
|
115
|
+
"count": 995
|
|
116
|
+
},
|
|
117
|
+
"Political Sciences": {
|
|
118
|
+
"count": 380
|
|
119
|
+
},
|
|
120
|
+
"Communication Studies": {
|
|
121
|
+
"count": 327
|
|
122
|
+
},
|
|
123
|
+
"Psychology": {
|
|
124
|
+
"count": 375
|
|
125
|
+
},
|
|
126
|
+
"Philosophy": {
|
|
127
|
+
"count": 434
|
|
128
|
+
},
|
|
129
|
+
"Art History": {
|
|
130
|
+
"count": 703
|
|
131
|
+
},
|
|
132
|
+
"History": {
|
|
133
|
+
"count": 522
|
|
134
|
+
},
|
|
135
|
+
"Law": {
|
|
136
|
+
"count": 2150
|
|
137
|
+
},
|
|
138
|
+
"Theology": {
|
|
139
|
+
"count": 116
|
|
140
|
+
},
|
|
141
|
+
"Social Health Sciences": {
|
|
142
|
+
"count": 489
|
|
143
|
+
},
|
|
144
|
+
"Criminology": {
|
|
145
|
+
"count": 576
|
|
146
|
+
},
|
|
147
|
+
"Literature": {
|
|
148
|
+
"count": 275
|
|
149
|
+
},
|
|
150
|
+
"Archaeology": {
|
|
151
|
+
"count": 235
|
|
152
|
+
}
|
|
153
|
+
}
|
|
154
|
+
}
|
|
155
|
+
}
|
|
156
|
+
}
|
|
@@ -0,0 +1,35 @@
|
|
|
1
|
+
{
|
|
2
|
+
"test": {
|
|
3
|
+
"num_samples": 2115,
|
|
4
|
+
"number_of_characters": 194569,
|
|
5
|
+
"unique_pairs": 2115,
|
|
6
|
+
"text1_statistics": {
|
|
7
|
+
"total_text_length": 100505,
|
|
8
|
+
"min_text_length": 10,
|
|
9
|
+
"average_text_length": 47.520094562647756,
|
|
10
|
+
"max_text_length": 158,
|
|
11
|
+
"unique_texts": 1769
|
|
12
|
+
},
|
|
13
|
+
"text2_statistics": {
|
|
14
|
+
"total_text_length": 94064,
|
|
15
|
+
"min_text_length": 10,
|
|
16
|
+
"average_text_length": 44.47470449172577,
|
|
17
|
+
"max_text_length": 158,
|
|
18
|
+
"unique_texts": 1738
|
|
19
|
+
},
|
|
20
|
+
"labels_statistics": {
|
|
21
|
+
"min_labels_per_text": 1,
|
|
22
|
+
"average_label_per_text": 1.0,
|
|
23
|
+
"max_labels_per_text": 1,
|
|
24
|
+
"unique_labels": 2,
|
|
25
|
+
"labels": {
|
|
26
|
+
"1": {
|
|
27
|
+
"count": 1404
|
|
28
|
+
},
|
|
29
|
+
"0": {
|
|
30
|
+
"count": 711
|
|
31
|
+
}
|
|
32
|
+
}
|
|
33
|
+
}
|
|
34
|
+
}
|
|
35
|
+
}
|
|
@@ -0,0 +1,35 @@
|
|
|
1
|
+
{
|
|
2
|
+
"test": {
|
|
3
|
+
"num_samples": 1004,
|
|
4
|
+
"number_of_characters": 103768,
|
|
5
|
+
"unique_pairs": 1004,
|
|
6
|
+
"text1_statistics": {
|
|
7
|
+
"total_text_length": 52390,
|
|
8
|
+
"min_text_length": 15,
|
|
9
|
+
"average_text_length": 52.18127490039841,
|
|
10
|
+
"max_text_length": 139,
|
|
11
|
+
"unique_texts": 851
|
|
12
|
+
},
|
|
13
|
+
"text2_statistics": {
|
|
14
|
+
"total_text_length": 51378,
|
|
15
|
+
"min_text_length": 9,
|
|
16
|
+
"average_text_length": 51.17330677290837,
|
|
17
|
+
"max_text_length": 131,
|
|
18
|
+
"unique_texts": 863
|
|
19
|
+
},
|
|
20
|
+
"labels_statistics": {
|
|
21
|
+
"min_labels_per_text": 1,
|
|
22
|
+
"average_label_per_text": 1.0,
|
|
23
|
+
"max_labels_per_text": 1,
|
|
24
|
+
"unique_labels": 2,
|
|
25
|
+
"labels": {
|
|
26
|
+
"1": {
|
|
27
|
+
"count": 502
|
|
28
|
+
},
|
|
29
|
+
"0": {
|
|
30
|
+
"count": 502
|
|
31
|
+
}
|
|
32
|
+
}
|
|
33
|
+
}
|
|
34
|
+
}
|
|
35
|
+
}
|
|
@@ -0,0 +1,30 @@
|
|
|
1
|
+
{
|
|
2
|
+
"test": {
|
|
3
|
+
"num_samples": 48416,
|
|
4
|
+
"number_of_characters": 59218442,
|
|
5
|
+
"documents_text_statistics": {
|
|
6
|
+
"total_text_length": 59096563,
|
|
7
|
+
"min_text_length": 1,
|
|
8
|
+
"average_text_length": 1246.3422262527417,
|
|
9
|
+
"max_text_length": 36320,
|
|
10
|
+
"unique_texts": 47416
|
|
11
|
+
},
|
|
12
|
+
"documents_image_statistics": null,
|
|
13
|
+
"queries_text_statistics": {
|
|
14
|
+
"total_text_length": 121879,
|
|
15
|
+
"min_text_length": 29,
|
|
16
|
+
"average_text_length": 121.879,
|
|
17
|
+
"max_text_length": 406,
|
|
18
|
+
"unique_texts": 1000
|
|
19
|
+
},
|
|
20
|
+
"queries_image_statistics": null,
|
|
21
|
+
"relevant_docs_statistics": {
|
|
22
|
+
"num_relevant_docs": 3048,
|
|
23
|
+
"min_relevant_docs_per_query": 1,
|
|
24
|
+
"average_relevant_docs_per_query": 3.048,
|
|
25
|
+
"max_relevant_docs_per_query": 5,
|
|
26
|
+
"unique_relevant_docs": 1042
|
|
27
|
+
},
|
|
28
|
+
"top_ranked_statistics": null
|
|
29
|
+
}
|
|
30
|
+
}
|
|
@@ -0,0 +1,30 @@
|
|
|
1
|
+
{
|
|
2
|
+
"test": {
|
|
3
|
+
"num_samples": 90470,
|
|
4
|
+
"number_of_characters": 30600110,
|
|
5
|
+
"documents_text_statistics": {
|
|
6
|
+
"total_text_length": 30586476,
|
|
7
|
+
"min_text_length": 8,
|
|
8
|
+
"average_text_length": 339.58561119129564,
|
|
9
|
+
"max_text_length": 5857,
|
|
10
|
+
"unique_texts": 90070
|
|
11
|
+
},
|
|
12
|
+
"documents_image_statistics": null,
|
|
13
|
+
"queries_text_statistics": {
|
|
14
|
+
"total_text_length": 13634,
|
|
15
|
+
"min_text_length": 6,
|
|
16
|
+
"average_text_length": 34.085,
|
|
17
|
+
"max_text_length": 88,
|
|
18
|
+
"unique_texts": 399
|
|
19
|
+
},
|
|
20
|
+
"queries_image_statistics": null,
|
|
21
|
+
"relevant_docs_statistics": {
|
|
22
|
+
"num_relevant_docs": 15286,
|
|
23
|
+
"min_relevant_docs_per_query": 21,
|
|
24
|
+
"average_relevant_docs_per_query": 38.215,
|
|
25
|
+
"max_relevant_docs_per_query": 1499,
|
|
26
|
+
"unique_relevant_docs": 40724
|
|
27
|
+
},
|
|
28
|
+
"top_ranked_statistics": null
|
|
29
|
+
}
|
|
30
|
+
}
|
|
@@ -0,0 +1,30 @@
|
|
|
1
|
+
{
|
|
2
|
+
"test": {
|
|
3
|
+
"num_samples": 256524,
|
|
4
|
+
"number_of_characters": 415016602,
|
|
5
|
+
"documents_text_statistics": {
|
|
6
|
+
"total_text_length": 414968472,
|
|
7
|
+
"min_text_length": 0,
|
|
8
|
+
"average_text_length": 1623.9902005291087,
|
|
9
|
+
"max_text_length": 29368,
|
|
10
|
+
"unique_texts": 255216
|
|
11
|
+
},
|
|
12
|
+
"documents_image_statistics": null,
|
|
13
|
+
"queries_text_statistics": {
|
|
14
|
+
"total_text_length": 48130,
|
|
15
|
+
"min_text_length": 11,
|
|
16
|
+
"average_text_length": 48.13,
|
|
17
|
+
"max_text_length": 110,
|
|
18
|
+
"unique_texts": 1000
|
|
19
|
+
},
|
|
20
|
+
"queries_image_statistics": null,
|
|
21
|
+
"relevant_docs_statistics": {
|
|
22
|
+
"num_relevant_docs": 1000,
|
|
23
|
+
"min_relevant_docs_per_query": 1,
|
|
24
|
+
"average_relevant_docs_per_query": 1.0,
|
|
25
|
+
"max_relevant_docs_per_query": 1,
|
|
26
|
+
"unique_relevant_docs": 1000
|
|
27
|
+
},
|
|
28
|
+
"top_ranked_statistics": null
|
|
29
|
+
}
|
|
30
|
+
}
|
|
@@ -0,0 +1,30 @@
|
|
|
1
|
+
{
|
|
2
|
+
"test": {
|
|
3
|
+
"num_samples": 164698,
|
|
4
|
+
"number_of_characters": 114050514,
|
|
5
|
+
"documents_text_statistics": {
|
|
6
|
+
"total_text_length": 114000894,
|
|
7
|
+
"min_text_length": 1,
|
|
8
|
+
"average_text_length": 696.4098156361104,
|
|
9
|
+
"max_text_length": 29033,
|
|
10
|
+
"unique_texts": 163698
|
|
11
|
+
},
|
|
12
|
+
"documents_image_statistics": null,
|
|
13
|
+
"queries_text_statistics": {
|
|
14
|
+
"total_text_length": 49620,
|
|
15
|
+
"min_text_length": 15,
|
|
16
|
+
"average_text_length": 49.62,
|
|
17
|
+
"max_text_length": 172,
|
|
18
|
+
"unique_texts": 997
|
|
19
|
+
},
|
|
20
|
+
"queries_image_statistics": null,
|
|
21
|
+
"relevant_docs_statistics": {
|
|
22
|
+
"num_relevant_docs": 1171,
|
|
23
|
+
"min_relevant_docs_per_query": 1,
|
|
24
|
+
"average_relevant_docs_per_query": 1.171,
|
|
25
|
+
"max_relevant_docs_per_query": 15,
|
|
26
|
+
"unique_relevant_docs": 677
|
|
27
|
+
},
|
|
28
|
+
"top_ranked_statistics": null
|
|
29
|
+
}
|
|
30
|
+
}
|
|
@@ -0,0 +1,30 @@
|
|
|
1
|
+
{
|
|
2
|
+
"test": {
|
|
3
|
+
"num_samples": 226621,
|
|
4
|
+
"number_of_characters": 84600866,
|
|
5
|
+
"documents_text_statistics": {
|
|
6
|
+
"total_text_length": 84508282,
|
|
7
|
+
"min_text_length": 8,
|
|
8
|
+
"average_text_length": 374.55858275603777,
|
|
9
|
+
"max_text_length": 3463,
|
|
10
|
+
"unique_texts": 225621
|
|
11
|
+
},
|
|
12
|
+
"documents_image_statistics": null,
|
|
13
|
+
"queries_text_statistics": {
|
|
14
|
+
"total_text_length": 92584,
|
|
15
|
+
"min_text_length": 34,
|
|
16
|
+
"average_text_length": 92.584,
|
|
17
|
+
"max_text_length": 288,
|
|
18
|
+
"unique_texts": 1000
|
|
19
|
+
},
|
|
20
|
+
"queries_image_statistics": null,
|
|
21
|
+
"relevant_docs_statistics": {
|
|
22
|
+
"num_relevant_docs": 2000,
|
|
23
|
+
"min_relevant_docs_per_query": 2,
|
|
24
|
+
"average_relevant_docs_per_query": 2.0,
|
|
25
|
+
"max_relevant_docs_per_query": 2,
|
|
26
|
+
"unique_relevant_docs": 1975
|
|
27
|
+
},
|
|
28
|
+
"top_ranked_statistics": null
|
|
29
|
+
}
|
|
30
|
+
}
|
|
@@ -0,0 +1,30 @@
|
|
|
1
|
+
{
|
|
2
|
+
"test": {
|
|
3
|
+
"num_samples": 30905,
|
|
4
|
+
"number_of_characters": 20629665,
|
|
5
|
+
"documents_text_statistics": {
|
|
6
|
+
"total_text_length": 20619027,
|
|
7
|
+
"min_text_length": 41,
|
|
8
|
+
"average_text_length": 669.3837288575788,
|
|
9
|
+
"max_text_length": 1716,
|
|
10
|
+
"unique_texts": 30172
|
|
11
|
+
},
|
|
12
|
+
"documents_image_statistics": null,
|
|
13
|
+
"queries_text_statistics": {
|
|
14
|
+
"total_text_length": 10638,
|
|
15
|
+
"min_text_length": 27,
|
|
16
|
+
"average_text_length": 104.29411764705883,
|
|
17
|
+
"max_text_length": 369,
|
|
18
|
+
"unique_texts": 102
|
|
19
|
+
},
|
|
20
|
+
"queries_image_statistics": null,
|
|
21
|
+
"relevant_docs_statistics": {
|
|
22
|
+
"num_relevant_docs": 157,
|
|
23
|
+
"min_relevant_docs_per_query": 1,
|
|
24
|
+
"average_relevant_docs_per_query": 1.5392156862745099,
|
|
25
|
+
"max_relevant_docs_per_query": 8,
|
|
26
|
+
"unique_relevant_docs": 148
|
|
27
|
+
},
|
|
28
|
+
"top_ranked_statistics": null
|
|
29
|
+
}
|
|
30
|
+
}
|
|
@@ -0,0 +1,30 @@
|
|
|
1
|
+
{
|
|
2
|
+
"test": {
|
|
3
|
+
"num_samples": 138633,
|
|
4
|
+
"number_of_characters": 59639635,
|
|
5
|
+
"documents_text_statistics": {
|
|
6
|
+
"total_text_length": 59576581,
|
|
7
|
+
"min_text_length": 2,
|
|
8
|
+
"average_text_length": 432.86552643624714,
|
|
9
|
+
"max_text_length": 16782,
|
|
10
|
+
"unique_texts": 122413
|
|
11
|
+
},
|
|
12
|
+
"documents_image_statistics": null,
|
|
13
|
+
"queries_text_statistics": {
|
|
14
|
+
"total_text_length": 63054,
|
|
15
|
+
"min_text_length": 9,
|
|
16
|
+
"average_text_length": 63.054,
|
|
17
|
+
"max_text_length": 286,
|
|
18
|
+
"unique_texts": 992
|
|
19
|
+
},
|
|
20
|
+
"queries_image_statistics": null,
|
|
21
|
+
"relevant_docs_statistics": {
|
|
22
|
+
"num_relevant_docs": 1000,
|
|
23
|
+
"min_relevant_docs_per_query": 1,
|
|
24
|
+
"average_relevant_docs_per_query": 1.0,
|
|
25
|
+
"max_relevant_docs_per_query": 1,
|
|
26
|
+
"unique_relevant_docs": 1000
|
|
27
|
+
},
|
|
28
|
+
"top_ranked_statistics": null
|
|
29
|
+
}
|
|
30
|
+
}
|
|
@@ -0,0 +1,30 @@
|
|
|
1
|
+
{
|
|
2
|
+
"test": {
|
|
3
|
+
"num_samples": 178163,
|
|
4
|
+
"number_of_characters": 10498457,
|
|
5
|
+
"documents_text_statistics": {
|
|
6
|
+
"total_text_length": 10447229,
|
|
7
|
+
"min_text_length": 1,
|
|
8
|
+
"average_text_length": 58.96958732918273,
|
|
9
|
+
"max_text_length": 581,
|
|
10
|
+
"unique_texts": 176849
|
|
11
|
+
},
|
|
12
|
+
"documents_image_statistics": null,
|
|
13
|
+
"queries_text_statistics": {
|
|
14
|
+
"total_text_length": 51228,
|
|
15
|
+
"min_text_length": 2,
|
|
16
|
+
"average_text_length": 51.228,
|
|
17
|
+
"max_text_length": 180,
|
|
18
|
+
"unique_texts": 1000
|
|
19
|
+
},
|
|
20
|
+
"queries_image_statistics": null,
|
|
21
|
+
"relevant_docs_statistics": {
|
|
22
|
+
"num_relevant_docs": 1641,
|
|
23
|
+
"min_relevant_docs_per_query": 1,
|
|
24
|
+
"average_relevant_docs_per_query": 1.641,
|
|
25
|
+
"max_relevant_docs_per_query": 34,
|
|
26
|
+
"unique_relevant_docs": 1641
|
|
27
|
+
},
|
|
28
|
+
"top_ranked_statistics": null
|
|
29
|
+
}
|
|
30
|
+
}
|
|
@@ -0,0 +1,30 @@
|
|
|
1
|
+
{
|
|
2
|
+
"test": {
|
|
3
|
+
"num_samples": 192237,
|
|
4
|
+
"number_of_characters": 234466370,
|
|
5
|
+
"documents_text_statistics": {
|
|
6
|
+
"total_text_length": 234404032,
|
|
7
|
+
"min_text_length": 0,
|
|
8
|
+
"average_text_length": 1225.7253146619116,
|
|
9
|
+
"max_text_length": 2000,
|
|
10
|
+
"unique_texts": 191237
|
|
11
|
+
},
|
|
12
|
+
"documents_image_statistics": null,
|
|
13
|
+
"queries_text_statistics": {
|
|
14
|
+
"total_text_length": 62338,
|
|
15
|
+
"min_text_length": 4,
|
|
16
|
+
"average_text_length": 62.338,
|
|
17
|
+
"max_text_length": 85,
|
|
18
|
+
"unique_texts": 1000
|
|
19
|
+
},
|
|
20
|
+
"queries_image_statistics": null,
|
|
21
|
+
"relevant_docs_statistics": {
|
|
22
|
+
"num_relevant_docs": 1000,
|
|
23
|
+
"min_relevant_docs_per_query": 1,
|
|
24
|
+
"average_relevant_docs_per_query": 1.0,
|
|
25
|
+
"max_relevant_docs_per_query": 1,
|
|
26
|
+
"unique_relevant_docs": 1000
|
|
27
|
+
},
|
|
28
|
+
"top_ranked_statistics": null
|
|
29
|
+
}
|
|
30
|
+
}
|
|
@@ -0,0 +1,30 @@
|
|
|
1
|
+
{
|
|
2
|
+
"test": {
|
|
3
|
+
"num_samples": 10318,
|
|
4
|
+
"number_of_characters": 7839416,
|
|
5
|
+
"documents_text_statistics": {
|
|
6
|
+
"total_text_length": 7765564,
|
|
7
|
+
"min_text_length": 9,
|
|
8
|
+
"average_text_length": 833.393861343636,
|
|
9
|
+
"max_text_length": 35146,
|
|
10
|
+
"unique_texts": 9123
|
|
11
|
+
},
|
|
12
|
+
"documents_image_statistics": null,
|
|
13
|
+
"queries_text_statistics": {
|
|
14
|
+
"total_text_length": 73852,
|
|
15
|
+
"min_text_length": 7,
|
|
16
|
+
"average_text_length": 73.852,
|
|
17
|
+
"max_text_length": 258,
|
|
18
|
+
"unique_texts": 999
|
|
19
|
+
},
|
|
20
|
+
"queries_image_statistics": null,
|
|
21
|
+
"relevant_docs_statistics": {
|
|
22
|
+
"num_relevant_docs": 1000,
|
|
23
|
+
"min_relevant_docs_per_query": 1,
|
|
24
|
+
"average_relevant_docs_per_query": 1.0,
|
|
25
|
+
"max_relevant_docs_per_query": 1,
|
|
26
|
+
"unique_relevant_docs": 1000
|
|
27
|
+
},
|
|
28
|
+
"top_ranked_statistics": null
|
|
29
|
+
}
|
|
30
|
+
}
|